INDEX

Explanations

phrases related to the name "Lamb"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Lamb" and its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 drift

-0.71

 Juda

-0.70

 Subtle

-0.68

PLIED

-0.67

 Occupations

-0.64

ãĥ¯

-0.64

 Kindle

-0.63

terday

-0.63

BOOK

-0.61

 ignorance

-0.60

POSITIVE LOGITS

da

0.99

inate

0.89

alle

0.88

osal

0.87

onde

0.84

alo

0.84

asso

0.84

rett

0.83

din

0.83

arse

0.81

Activations Density 0.019%

phrases related to the name "Lamb"

references to the name "Lamb" and its variations

No Comments

No Known Activations